clear-writing-en
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for text editing and report writing. No executable code or scripts are included.
- [PROMPT_INJECTION]: The skill contains explicit defensive instructions that restrict the agent's scope. It directs the agent to preserve code, identifiers, commands, and logs, and explicitly states that a writing request does not authorize the execution of actions described within the text.
- [INDIRECT_PROMPT_INJECTION]: Although the skill is designed to process user-provided text (a potential injection surface), it lacks capabilities that could be abused, such as network access or file system modifications. Furthermore, it includes specific constraints to ignore and preserve non-prose elements like commands and paths.
- [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or data exfiltration patterns were detected. The skill is focused on stylistic improvement of provided text.
Audit Metadata